Final Exam Assigned: 11/21/02 Due: 12/05/02 at 2:30pm
|
|
- Deborah McGee
- 5 years ago
- Views:
Transcription
1 6.801/6.866 Machine Vision Final Exam Assigned: 11/21/02 Due: 12/05/02 at 2:30pm Problem 1 Line Fitting through Segmentation (Matlab) a) Write a Matlab function to generate noisy line segment data with outliers, similar to that shown in Figure 15.9/ You should presume Gaussian distributed noise (in and uniformly distributed outlier noise. Your function should have the following syntax: function [X,Y] = create_line(a,b,x1,x2,var,perc_out,range_out) The output parameters [X,Y] are samples of the line y = ax + b between x=x1 and x=x2. The input parameter var is the variance of the Gaussian distributed noise, perc_out is the percentage of outliers and range_out is the outlier range. For each implementation (b), (c), (d) and (e), below, (i) Plot cases where your implementation succeeds; (ii) Plot cases where your implementation fails and discuss why it fails; (iii) Discuss the effect of each input parameter on the algorithm; (iv) Submit your files and print a copy of your code. b) Implement a simple least-squares fit of the line. Your function should have the following syntax: function [a, b] = fitline(x, Y) c) Implement a Hough transform accumulator array, and a simple maximum peak finder. Test this for different granularities of parameter sampling on single-line datasets with varying amounts of normal and outlier noise. Your function should have the following syntax: function [a,b,m] = hough(x, Y, r_min, r_max, r_step, theta_step) where [r_min, r_max] is the range of the line distance from the origin, r_step is the incremental step between radius samples and theta_step is the incremental step between angle samples. The mask vector M is set to 1 when the point is an inlier and 0 when an outlier. d) Implement a RANSAC approach (Algorithm 15.4) using the least squares distance metric described in section Test it on single-line datasets with varying amounts of normal and outlier noise. Your function should have the following syntax: function [a, b, M] = ransac(x, Y, n, max_it, thresh, min_inliers) where n is the number of points sub-sampled to fit a line, max_it is the maximum number of iterations, thresh is the threshold used to identify inliers and min_in is the minimum number of inliers.
2 e) Implement an EM approach to estimate a fixed number of noisy lines (Algorithm 16.4) and add an outlier model (section ). The simplest way to do this is to consider a mixture model with the last mixture component is not a line, but a process that generates outlier points with uniform probability. Your function should have the following syntax: function [a, b, W] = em(x, Y, perc_out, range_out, W_initial) where perc_out models frequency with which outliers occur, range_out is the range of the uniform outlier process and the vector W_initial is the initial weight values. The output parameter W is the final weight vector. Don t forget to define a convergence criterion. Test your implementation on single- and multiple-line datasets with varying amounts of normal and outlier noise. f) Outline a possible graph theoretic approach to segmenting this data using a normalized cut criterion. Problem 2 Line Fitting through Filtering (Matlab) In this problem, we view the line fitting task of Problem 1 as an online filtering problem. The x coordinate of each point on the line will be treated as the (discrete) time variable. We will then estimate the sequence of y coordinates based on noisy measurements generated as in Problem 1(a). For both of the implemented algorithms, present your results as in Problem 1, (i)-(iv). a) Implement the Kalman filter for tracking linear dynamic systems based on observations corrupted by Gaussian noise. Assume the line is generated by a constant velocity state space model. Your filtering function should have the following syntax: function xhat = kalman(y,d,sigmastate,m,sigmaobs,sigma0) Here, Y is a vector of scalar observations, (D,SigmaState,M,SigmaObs) are the standard state space model parameters, and Sigma0 is the covariance of the (zero mean) initial state. The output xhat should be a matrix where each column gives the mean estimate of the hidden state at a different point in time. Choose values for the system noise parameters that are appropriate to the line fitting problem. In particular, you should have a large initial state variance, but a fairly small process noise variance. Test your Kalman filter implementation on measurements containing only the assumed Gaussian noise, and also on data sets with large numbers of outliers. b) Particle filters do not share the Kalman filter s restriction to Gaussian observations. Implement the standard particle filtering algorithm (Forsyth & Ponce, Extra Chapter 2, Alg. 2.5) for tracking a linear dynamical system based on a sequence of scalar, non-gaussian observations. Your filtering function should have the following syntax: function xhat = pfilter(y,d,sigmastate,m,sigmaobs,sigma0, N,perc_out,range_out)
3 The first six parameters are the same as for the Kalman filter, N is the number of particles, and (perc_out,range_out) are the parameters of the outlier process. Your particle filter implementation should resample at every iteration, and use the appropriately weighted average of particle locations as its best estimate of the line position. Test the particle filter on the same measurement sequences used for the Kalman filter. Perform five independent runs of the particle filter for each of three different particle set sizes N = 20, 100, 500, and plot the estimated line positions. Problem 3 Steerable Filters Steerable pyramids received their name because the oriented filters at any one spatial scale form a "steerable basis set". They are all identical copies of the same filter, rotated to different orientations. One can synthesize that filter rotated to any orientation by taking an appropriate linear combination of the basis filters. This lets one analyze oriented filter response not just at a discrete set of orientations, but over the continuous range of possible orientations. Let F θ ( x, be a filter kernel, F( x,, rotated through an angle, θ. For now, we ignore sampling issues and work in a continuous (x, space. F( x, is a steerable filter requiring M basis filters if we can write F θ ( x, = M i= 1 k ( θ ) F i θ i ( x, θ Here, F i ( x, are the basis filters and k i (θ ) are called the interpolation functions. a) The simplest possible steerable filter is the directional derivative of a radially symmetric function G(r), where r ( x + y ) = x y. Let G ( r) = e be a Gaussian function. Show that G is a steerable filter. Give a set of basis filters and x interpolation functions using the smallest possible number of terms M. 2 b) Show that the second derivative of a Gaussian G x 2 is also a steerable filter. Give a set of basis filters and interpolation functions using the smallest possible number of terms M. c) Describe how sampling of these continuous functions at discrete locations on the pixel lattice affects steerability. Note: In the general case, the basis filters don't need to be identical copies of the filter to be synthesized, nor do the steered filters need to be derivatives of radially symmetric functions. Problem 4 Mosaics of kite aerial photographs You attach a camera to a kite, send it up, and take many pictures of the ground, each from a different position, orientation, and elevation of the camera. Then, you want to make a composite image, overlaying the photographs into a single image. (See for example or 2 2
4 This problem examines under what conditions the overlaid images can be made to fit together exactly. (See the figures for a visual description of the problem.) kite and camera (time 1) kite and camera (time 2) photograph from camera at time 1 photograph from camera at time 2 We have two images taken of the same piece of land and we want to know under what combinations of (i) assumed camera model, (ii) assumed terrain model, and (iii) method of compositing the pictures can the two images be made to look identical in their region of overlap. After you take the digital photographs, you form a mosaic using some image editing program. Assume the objects on the ground are stationary, and we only consider geometric effects, not photometric effects. (In other words, the objects in the photographs must line up in the mosaic, but their intensities may differ in the different images.) (i) camera models: we can assume either perspective projection, or weak perspective projection. (ii) terrain models: we can assume that the land being photographed lies in a plane, or has arbitrary 3-d shape. (iii) method of compositing the pictures: say we paste the photographs into the composite bitmap, then have a choice of two different methods of
5 adjusting the pasted photographs, corresponding to a choice of two different image manipulation programs. Using program A, we can translate, rotate, and uniformly scale each pasted image as we put it into the composite. Using program B, we can make all those changes and more: we can independently specify the location of each of the 4 corners of the pasted image (i.e., we can map the image into an arbitrarily shaped quadrilateral area, linearly interpolating the pixel positions inside the pasted image). 2 different methods of compositing the pictures Composition method 1 allows scaling and rotation of the photographs: Composition method 2 allows arbitrary scaling, rotation, and linear warping of the photographs to fill an arbitrary quadrilateral: With two choices each for the camera, terrain, and image composition models, we have 8 possible systems to consider. Under which of those 8 systems can the overlapped pictures always be made to agree exactly within their regions of overlap? Explain your reasoning and justify your answers. You want perfect overlay of the two photographs in the region where they overlap in the mosaic.
6 Problem 5 Projective Geometry Exercise 13.6 from Computer Vision: A Modern Approach (Forsyth and Ponce) Problem 6 State Space Observability Consider the following linear state space model: T x t+1 = Dt xt y t = M t xt Here, the measurement y t is a one-dimensional scalar for each t, and x t is a k-dimensional vector. We say that this model is observable is the state can be reconstructed from any sequence of k measurements. a) Show that the model is observable if and only if the following matrix has full rank: T M t T M t+ 1Dt T M t+ 2Dt + 1Dt M T M t+ k 1Dt + k 2 LDt b) Consider a point drifting in 3D ( D t = I3 ), with a periodically varying observation [ ] T 3 = [ ] T +, [ ] T matrix: M k 0 0 1, M = 3k M 3 k+ 2 = Show that the model is observable. c) Show that a point moving with constant velocity in an arbitrary number of dimensions, with the observation matrix reporting position only, is observable. d) Show that a point moving with constant acceleration in an arbitrary number of dimensions, with the observation matrix reporting position only, is observable.
CSE 252B: Computer Vision II
CSE 252B: Computer Vision II Lecturer: Serge Belongie Scribes: Jeremy Pollock and Neil Alldrin LECTURE 14 Robust Feature Matching 14.1. Introduction Last lecture we learned how to find interest points
More informationCS 231A Computer Vision (Winter 2014) Problem Set 3
CS 231A Computer Vision (Winter 2014) Problem Set 3 Due: Feb. 18 th, 2015 (11:59pm) 1 Single Object Recognition Via SIFT (45 points) In his 2004 SIFT paper, David Lowe demonstrates impressive object recognition
More informationFeature Detectors and Descriptors: Corners, Lines, etc.
Feature Detectors and Descriptors: Corners, Lines, etc. Edges vs. Corners Edges = maxima in intensity gradient Edges vs. Corners Corners = lots of variation in direction of gradient in a small neighborhood
More informationModel Fitting. Introduction to Computer Vision CSE 152 Lecture 11
Model Fitting CSE 152 Lecture 11 Announcements Homework 3 is due May 9, 11:59 PM Reading: Chapter 10: Grouping and Model Fitting What to do with edges? Segment linked edge chains into curve features (e.g.,
More informationStraight Lines and Hough
09/30/11 Straight Lines and Hough Computer Vision CS 143, Brown James Hays Many slides from Derek Hoiem, Lana Lazebnik, Steve Seitz, David Forsyth, David Lowe, Fei-Fei Li Project 1 A few project highlights
More informationComputer Vision 6 Segmentation by Fitting
Computer Vision 6 Segmentation by Fitting MAP-I Doctoral Programme Miguel Tavares Coimbra Outline The Hough Transform Fitting Lines Fitting Curves Fitting as a Probabilistic Inference Problem Acknowledgements:
More informationCSE 527: Introduction to Computer Vision
CSE 527: Introduction to Computer Vision Week 5 - Class 1: Matching, Stitching, Registration September 26th, 2017 ??? Recap Today Feature Matching Image Alignment Panoramas HW2! Feature Matches Feature
More informationCS231A Midterm Review. Friday 5/6/2016
CS231A Midterm Review Friday 5/6/2016 Outline General Logistics Camera Models Non-perspective cameras Calibration Single View Metrology Epipolar Geometry Structure from Motion Active Stereo and Volumetric
More informationEE795: Computer Vision and Intelligent Systems
EE795: Computer Vision and Intelligent Systems Spring 2012 TTh 17:30-18:45 FDH 204 Lecture 10 130221 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Review Canny Edge Detector Hough Transform Feature-Based
More informationImage warping and stitching
Image warping and stitching Thurs Oct 15 Last time Feature-based alignment 2D transformations Affine fit RANSAC 1 Robust feature-based alignment Extract features Compute putative matches Loop: Hypothesize
More informationSchedule for Rest of Semester
Schedule for Rest of Semester Date Lecture Topic 11/20 24 Texture 11/27 25 Review of Statistics & Linear Algebra, Eigenvectors 11/29 26 Eigenvector expansions, Pattern Recognition 12/4 27 Cameras & calibration
More informationImage warping and stitching
Image warping and stitching May 4 th, 2017 Yong Jae Lee UC Davis Last time Interactive segmentation Feature-based alignment 2D transformations Affine fit RANSAC 2 Alignment problem In alignment, we will
More informationSIFT: SCALE INVARIANT FEATURE TRANSFORM SURF: SPEEDED UP ROBUST FEATURES BASHAR ALSADIK EOS DEPT. TOPMAP M13 3D GEOINFORMATION FROM IMAGES 2014
SIFT: SCALE INVARIANT FEATURE TRANSFORM SURF: SPEEDED UP ROBUST FEATURES BASHAR ALSADIK EOS DEPT. TOPMAP M13 3D GEOINFORMATION FROM IMAGES 2014 SIFT SIFT: Scale Invariant Feature Transform; transform image
More informationCS 231A Computer Vision (Fall 2012) Problem Set 3
CS 231A Computer Vision (Fall 2012) Problem Set 3 Due: Nov. 13 th, 2012 (2:15pm) 1 Probabilistic Recursion for Tracking (20 points) In this problem you will derive a method for tracking a point of interest
More informationImage Transfer Methods. Satya Prakash Mallick Jan 28 th, 2003
Image Transfer Methods Satya Prakash Mallick Jan 28 th, 2003 Objective Given two or more images of the same scene, the objective is to synthesize a novel view of the scene from a view point where there
More informationFeature Matching and RANSAC
Feature Matching and RANSAC Recognising Panoramas. [M. Brown and D. Lowe,ICCV 2003] [Brown, Szeliski, Winder, CVPR 2005] with a lot of slides stolen from Steve Seitz, Rick Szeliski, A. Efros Introduction
More informationObject Recognition with Invariant Features
Object Recognition with Invariant Features Definition: Identify objects or scenes and determine their pose and model parameters Applications Industrial automation and inspection Mobile robots, toys, user
More informationFinal Exam Schedule. Final exam has been scheduled. 12:30 pm 3:00 pm, May 7. Location: INNOVA It will cover all the topics discussed in class
Final Exam Schedule Final exam has been scheduled 12:30 pm 3:00 pm, May 7 Location: INNOVA 1400 It will cover all the topics discussed in class One page double-sided cheat sheet is allowed A calculator
More informationImage warping and stitching
Image warping and stitching May 5 th, 2015 Yong Jae Lee UC Davis PS2 due next Friday Announcements 2 Last time Interactive segmentation Feature-based alignment 2D transformations Affine fit RANSAC 3 Alignment
More informationCS 231A Computer Vision (Winter 2018) Problem Set 3
CS 231A Computer Vision (Winter 2018) Problem Set 3 Due: Feb 28, 2018 (11:59pm) 1 Space Carving (25 points) Dense 3D reconstruction is a difficult problem, as tackling it from the Structure from Motion
More informationContents. 1 Introduction Background Organization Features... 7
Contents 1 Introduction... 1 1.1 Background.... 1 1.2 Organization... 2 1.3 Features... 7 Part I Fundamental Algorithms for Computer Vision 2 Ellipse Fitting... 11 2.1 Representation of Ellipses.... 11
More informationUncertainties: Representation and Propagation & Line Extraction from Range data
41 Uncertainties: Representation and Propagation & Line Extraction from Range data 42 Uncertainty Representation Section 4.1.3 of the book Sensing in the real world is always uncertain How can uncertainty
More informationSYDE Winter 2011 Introduction to Pattern Recognition. Clustering
SYDE 372 - Winter 2011 Introduction to Pattern Recognition Clustering Alexander Wong Department of Systems Design Engineering University of Waterloo Outline 1 2 3 4 5 All the approaches we have learned
More informationMosaics. Today s Readings
Mosaics VR Seattle: http://www.vrseattle.com/ Full screen panoramas (cubic): http://www.panoramas.dk/ Mars: http://www.panoramas.dk/fullscreen3/f2_mars97.html Today s Readings Szeliski and Shum paper (sections
More informationThree-Dimensional Sensors Lecture 6: Point-Cloud Registration
Three-Dimensional Sensors Lecture 6: Point-Cloud Registration Radu Horaud INRIA Grenoble Rhone-Alpes, France Radu.Horaud@inria.fr http://perception.inrialpes.fr/ Point-Cloud Registration Methods Fuse data
More informationOutline 7/2/201011/6/
Outline Pattern recognition in computer vision Background on the development of SIFT SIFT algorithm and some of its variations Computational considerations (SURF) Potential improvement Summary 01 2 Pattern
More informationToday s lecture. Image Alignment and Stitching. Readings. Motion models
Today s lecture Image Alignment and Stitching Computer Vision CSE576, Spring 2005 Richard Szeliski Image alignment and stitching motion models cylindrical and spherical warping point-based alignment global
More informationEE795: Computer Vision and Intelligent Systems
EE795: Computer Vision and Intelligent Systems Spring 2012 TTh 17:30-18:45 FDH 204 Lecture 12 130228 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Review Panoramas, Mosaics, Stitching Two View Geometry
More informationFitting. Choose a parametric object/some objects to represent a set of tokens Most interesting case is when criterion is not local
Fitting Choose a parametric object/some objects to represent a set of tokens Most interesting case is when criterion is not local can t tell whether a set of points lies on a line by looking only at each
More informationMixture Models and EM
Mixture Models and EM Goal: Introduction to probabilistic mixture models and the expectationmaximization (EM) algorithm. Motivation: simultaneous fitting of multiple model instances unsupervised clustering
More informationVisual Odometry. Features, Tracking, Essential Matrix, and RANSAC. Stephan Weiss Computer Vision Group NASA-JPL / CalTech
Visual Odometry Features, Tracking, Essential Matrix, and RANSAC Stephan Weiss Computer Vision Group NASA-JPL / CalTech Stephan.Weiss@ieee.org (c) 2013. Government sponsorship acknowledged. Outline The
More informationFinal Exam Study Guide
Final Exam Study Guide Exam Window: 28th April, 12:00am EST to 30th April, 11:59pm EST Description As indicated in class the goal of the exam is to encourage you to review the material from the course.
More informationGeneralized Hough Transform, line fitting
Generalized Hough Transform, line fitting Introduction to Computer Vision CSE 152 Lecture 11-a Announcements Assignment 2: Due today Midterm: Thursday, May 10 in class Non-maximum suppression For every
More informationHomographies and RANSAC
Homographies and RANSAC Computer vision 6.869 Bill Freeman and Antonio Torralba March 30, 2011 Homographies and RANSAC Homographies RANSAC Building panoramas Phototourism 2 Depth-based ambiguity of position
More informationUNIVERSITY OF OSLO. Faculty of Mathematics and Natural Sciences
UNIVERSITY OF OSLO Faculty of Mathematics and Natural Sciences Exam: INF 4300 / INF 9305 Digital image analysis Date: Thursday December 21, 2017 Exam hours: 09.00-13.00 (4 hours) Number of pages: 8 pages
More informationMotion Tracking and Event Understanding in Video Sequences
Motion Tracking and Event Understanding in Video Sequences Isaac Cohen Elaine Kang, Jinman Kang Institute for Robotics and Intelligent Systems University of Southern California Los Angeles, CA Objectives!
More informationTightly-Integrated Visual and Inertial Navigation for Pinpoint Landing on Rugged Terrains
Tightly-Integrated Visual and Inertial Navigation for Pinpoint Landing on Rugged Terrains PhD student: Jeff DELAUNE ONERA Director: Guy LE BESNERAIS ONERA Advisors: Jean-Loup FARGES Clément BOURDARIAS
More informationCS 223B Computer Vision Problem Set 3
CS 223B Computer Vision Problem Set 3 Due: Feb. 22 nd, 2011 1 Probabilistic Recursion for Tracking In this problem you will derive a method for tracking a point of interest through a sequence of images.
More informationEdge detection. Convert a 2D image into a set of curves. Extracts salient features of the scene More compact than pixels
Edge Detection Edge detection Convert a 2D image into a set of curves Extracts salient features of the scene More compact than pixels Origin of Edges surface normal discontinuity depth discontinuity surface
More informationMidterm Examination CS 534: Computational Photography
Midterm Examination CS 534: Computational Photography November 3, 2016 NAME: Problem Score Max Score 1 6 2 8 3 9 4 12 5 4 6 13 7 7 8 6 9 9 10 6 11 14 12 6 Total 100 1 of 8 1. [6] (a) [3] What camera setting(s)
More informationCOMPARATIVE STUDY OF DIFFERENT APPROACHES FOR EFFICIENT RECTIFICATION UNDER GENERAL MOTION
COMPARATIVE STUDY OF DIFFERENT APPROACHES FOR EFFICIENT RECTIFICATION UNDER GENERAL MOTION Mr.V.SRINIVASA RAO 1 Prof.A.SATYA KALYAN 2 DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING PRASAD V POTLURI SIDDHARTHA
More informationLocally Weighted Least Squares Regression for Image Denoising, Reconstruction and Up-sampling
Locally Weighted Least Squares Regression for Image Denoising, Reconstruction and Up-sampling Moritz Baecher May 15, 29 1 Introduction Edge-preserving smoothing and super-resolution are classic and important
More informationCPSC 425: Computer Vision
CPSC 425: Computer Vision Image Credit: https://docs.adaptive-vision.com/4.7/studio/machine_vision_guide/templatematching.html Lecture 9: Template Matching (cont.) and Scaled Representations ( unless otherwise
More informationFitting D.A. Forsyth, CS 543
Fitting D.A. Forsyth, CS 543 Fitting Choose a parametric object/some objects to represent a set of tokens Most interesting case is when criterion is not local can t tell whether a set of points lies on
More informationEE795: Computer Vision and Intelligent Systems
EE795: Computer Vision and Intelligent Systems Spring 2012 TTh 17:30-18:45 FDH 204 Lecture 14 130307 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Review Stereo Dense Motion Estimation Translational
More informationMultimedia Computing: Algorithms, Systems, and Applications: Edge Detection
Multimedia Computing: Algorithms, Systems, and Applications: Edge Detection By Dr. Yu Cao Department of Computer Science The University of Massachusetts Lowell Lowell, MA 01854, USA Part of the slides
More informationCS443: Digital Imaging and Multimedia Perceptual Grouping Detecting Lines and Simple Curves
CS443: Digital Imaging and Multimedia Perceptual Grouping Detecting Lines and Simple Curves Spring 2008 Ahmed Elgammal Dept. of Computer Science Rutgers University Outlines Perceptual Grouping and Segmentation
More informationHomography estimation
RANSAC continued Homography estimation x w? ~x img H~x w Homography estimation? x img ~x w = H 1 ~x img Homography estimation (0,0) (1,0) (6.4,2.8) (8.0,2.9) (5.6, 4.0) (7.8, 4.2) (0,1) (1,1) Ah =0s.tkhk
More informationEXAM SOLUTIONS. Image Processing and Computer Vision Course 2D1421 Monday, 13 th of March 2006,
School of Computer Science and Communication, KTH Danica Kragic EXAM SOLUTIONS Image Processing and Computer Vision Course 2D1421 Monday, 13 th of March 2006, 14.00 19.00 Grade table 0-25 U 26-35 3 36-45
More informationPanoramic Image Stitching
Mcgill University Panoramic Image Stitching by Kai Wang Pengbo Li A report submitted in fulfillment for the COMP 558 Final project in the Faculty of Computer Science April 2013 Mcgill University Abstract
More informationFeature Tracking and Optical Flow
Feature Tracking and Optical Flow Prof. D. Stricker Doz. G. Bleser Many slides adapted from James Hays, Derek Hoeim, Lana Lazebnik, Silvio Saverse, who in turn adapted slides from Steve Seitz, Rick Szeliski,
More informationProblem Set 3 CMSC 426 Due: Thursday, April 3
Problem Set 3 CMSC 426 Due: Thursday, April 3 Overview: This problem set will work a little different. There will be a standard part, and an advanced part. Students may choose to do either part. Alternately,
More informationFeature Matching and Robust Fitting
Feature Matching and Robust Fitting Computer Vision CS 143, Brown Read Szeliski 4.1 James Hays Acknowledgment: Many slides from Derek Hoiem and Grauman&Leibe 2008 AAAI Tutorial Project 2 questions? This
More informationInstance-level recognition
Instance-level recognition 1) Local invariant features 2) Matching and recognition with local features 3) Efficient visual search 4) Very large scale indexing Matching of descriptors Matching and 3D reconstruction
More informationFeature Tracking and Optical Flow
Feature Tracking and Optical Flow Prof. D. Stricker Doz. G. Bleser Many slides adapted from James Hays, Derek Hoeim, Lana Lazebnik, Silvio Saverse, who 1 in turn adapted slides from Steve Seitz, Rick Szeliski,
More informationFitting. Lecture 8. Cristian Sminchisescu. Slide credits: K. Grauman, S. Seitz, S. Lazebnik, D. Forsyth, J. Ponce
Fitting Lecture 8 Cristian Sminchisescu Slide credits: K. Grauman, S. Seitz, S. Lazebnik, D. Forsyth, J. Ponce Fitting We want to associate a model with observed features [Fig from Marszalek & Schmid,
More information3D Reconstruction from Two Views
3D Reconstruction from Two Views Huy Bui UIUC huybui1@illinois.edu Yiyi Huang UIUC huang85@illinois.edu Abstract In this project, we study a method to reconstruct a 3D scene from two views. First, we extract
More informationFitting: The Hough transform
Fitting: The Hough transform Voting schemes Let each feature vote for all the models that are compatible with it Hopefully the noise features will not vote consistently for any single model Missing data
More informationLecture 16: Computer Vision
CS4442/9542b: Artificial Intelligence II Prof. Olga Veksler Lecture 16: Computer Vision Motion Slides are from Steve Seitz (UW), David Jacobs (UMD) Outline Motion Estimation Motion Field Optical Flow Field
More informationOptical Flow Estimation
Optical Flow Estimation Goal: Introduction to image motion and 2D optical flow estimation. Motivation: Motion is a rich source of information about the world: segmentation surface structure from parallax
More informationPerception. Autonomous Mobile Robots. Sensors Vision Uncertainties, Line extraction from laser scans. Autonomous Systems Lab. Zürich.
Autonomous Mobile Robots Localization "Position" Global Map Cognition Environment Model Local Map Path Perception Real World Environment Motion Control Perception Sensors Vision Uncertainties, Line extraction
More informationFundamentals of Digital Image Processing
\L\.6 Gw.i Fundamentals of Digital Image Processing A Practical Approach with Examples in Matlab Chris Solomon School of Physical Sciences, University of Kent, Canterbury, UK Toby Breckon School of Engineering,
More informationLecture 16: Computer Vision
CS442/542b: Artificial ntelligence Prof. Olga Veksler Lecture 16: Computer Vision Motion Slides are from Steve Seitz (UW), David Jacobs (UMD) Outline Motion Estimation Motion Field Optical Flow Field Methods
More informationCamera Geometry II. COS 429 Princeton University
Camera Geometry II COS 429 Princeton University Outline Projective geometry Vanishing points Application: camera calibration Application: single-view metrology Epipolar geometry Application: stereo correspondence
More informationEdge Detection. Announcements. Edge detection. Origin of Edges. Mailing list: you should have received messages
Announcements Mailing list: csep576@cs.washington.edu you should have received messages Project 1 out today (due in two weeks) Carpools Edge Detection From Sandlot Science Today s reading Forsyth, chapters
More informationBSB663 Image Processing Pinar Duygulu. Slides are adapted from Selim Aksoy
BSB663 Image Processing Pinar Duygulu Slides are adapted from Selim Aksoy Image matching Image matching is a fundamental aspect of many problems in computer vision. Object or scene recognition Solving
More informationhuman vision: grouping k-means clustering graph-theoretic clustering Hough transform line fitting RANSAC
COS 429: COMPUTER VISON Segmentation human vision: grouping k-means clustering graph-theoretic clustering Hough transform line fitting RANSAC Reading: Chapters 14, 15 Some of the slides are credited to:
More informationEdge and corner detection
Edge and corner detection Prof. Stricker Doz. G. Bleser Computer Vision: Object and People Tracking Goals Where is the information in an image? How is an object characterized? How can I find measurements
More informationImage stitching. Announcements. Outline. Image stitching
Announcements Image stitching Project #1 was due yesterday. Project #2 handout will be available on the web later tomorrow. I will set up a webpage for artifact voting soon. Digital Visual Effects, Spring
More information3. Data Structures for Image Analysis L AK S H M O U. E D U
3. Data Structures for Image Analysis L AK S H M AN @ O U. E D U Different formulations Can be advantageous to treat a spatial grid as a: Levelset Matrix Markov chain Topographic map Relational structure
More informationStereo and Epipolar geometry
Previously Image Primitives (feature points, lines, contours) Today: Stereo and Epipolar geometry How to match primitives between two (multiple) views) Goals: 3D reconstruction, recognition Jana Kosecka
More informationInstance-level recognition
Instance-level recognition 1) Local invariant features 2) Matching and recognition with local features 3) Efficient visual search 4) Very large scale indexing Matching of descriptors Matching and 3D reconstruction
More informationIntroduction. Chapter Overview
Chapter 1 Introduction The Hough Transform is an algorithm presented by Paul Hough in 1962 for the detection of features of a particular shape like lines or circles in digitalized images. In its classical
More informationMETR4202: ROBOTICS & AUTOMATION
Sort Pattern A This exam paper must not be removed from the venue School of Information Technology and Electrical Engineering Mid-Term Quiz METR4202: ROBOTICS & AUTOMATION September 20, 2017 First Name:
More informationFactorization with Missing and Noisy Data
Factorization with Missing and Noisy Data Carme Julià, Angel Sappa, Felipe Lumbreras, Joan Serrat, and Antonio López Computer Vision Center and Computer Science Department, Universitat Autònoma de Barcelona,
More informationLecture 8 Fitting and Matching
Lecture 8 Fitting and Matching Problem formulation Least square methods RANSAC Hough transforms Multi-model fitting Fitting helps matching! Reading: [HZ] Chapter: 4 Estimation 2D projective transformation
More informationCOMPUTER AND ROBOT VISION
VOLUME COMPUTER AND ROBOT VISION Robert M. Haralick University of Washington Linda G. Shapiro University of Washington A^ ADDISON-WESLEY PUBLISHING COMPANY Reading, Massachusetts Menlo Park, California
More informationCS443: Digital Imaging and Multimedia Binary Image Analysis. Spring 2008 Ahmed Elgammal Dept. of Computer Science Rutgers University
CS443: Digital Imaging and Multimedia Binary Image Analysis Spring 2008 Ahmed Elgammal Dept. of Computer Science Rutgers University Outlines A Simple Machine Vision System Image segmentation by thresholding
More informationComputer Vision CSCI-GA Assignment 1.
Computer Vision CSCI-GA.2272-001 Assignment 1. September 22, 2017 Introduction This assignment explores various methods for aligning images and feature extraction. There are four parts to the assignment:
More information1 CSE 252A Computer Vision I Fall 2017
Assignment 1 CSE A Computer Vision I Fall 01 1.1 Assignment This assignment contains theoretical and programming exercises. If you plan to submit hand written answers for theoretical exercises, please
More informationCHAPTER 1 INTRODUCTION
1 CHAPTER 1 INTRODUCTION Table of Contents Page No. 1 INTRODUCTION 1.1 Problem overview 2 1.2 Research objective 3 1.3 Thesis outline 7 2 1. INTRODUCTION 1.1 PROBLEM OVERVIEW The process of mapping and
More informationContents I IMAGE FORMATION 1
Contents I IMAGE FORMATION 1 1 Geometric Camera Models 3 1.1 Image Formation............................. 4 1.1.1 Pinhole Perspective....................... 4 1.1.2 Weak Perspective.........................
More informationCS 231A Computer Vision (Winter 2015) Problem Set 2
CS 231A Computer Vision (Winter 2015) Problem Set 2 Due Feb 9 th 2015 11:59pm 1 Fundamental Matrix (20 points) In this question, you will explore some properties of fundamental matrix and derive a minimal
More informationHOUGH TRANSFORM CS 6350 C V
HOUGH TRANSFORM CS 6350 C V HOUGH TRANSFORM The problem: Given a set of points in 2-D, find if a sub-set of these points, fall on a LINE. Hough Transform One powerful global method for detecting edges
More informationObject recognition of Glagolitic characters using Sift and Ransac
Object recognition of Glagolitic characters using Sift and Ransac Images in database: Glagolitic alphabet characters. Algorithm 1) Prepare a database of images. Images characteristics : 1. Scale changed
More informationINFO0948 Fitting and Shape Matching
INFO0948 Fitting and Shape Matching Renaud Detry University of Liège, Belgium Updated March 31, 2015 1 / 33 These slides are based on the following book: D. Forsyth and J. Ponce. Computer vision: a modern
More informationEE640 FINAL PROJECT HEADS OR TAILS
EE640 FINAL PROJECT HEADS OR TAILS By Laurence Hassebrook Initiated: April 2015, updated April 27 Contents 1. SUMMARY... 1 2. EXPECTATIONS... 2 3. INPUT DATA BASE... 2 4. PREPROCESSING... 4 4.1 Surface
More informationAutomatic Photo Popup
Automatic Photo Popup Derek Hoiem Alexei A. Efros Martial Hebert Carnegie Mellon University What Is Automatic Photo Popup Introduction Creating 3D models from images is a complex process Time-consuming
More informationAnnouncements. Hough Transform [ Patented 1962 ] Generalized Hough Transform, line fitting. Assignment 2: Due today Midterm: Thursday, May 5 in class
Announcements Generalized Hough Transform, line fitting Assignment 2: Due today Midterm: Thursday, May 5 in class Introduction to Computer Vision CSE 152 Lecture 11a What is region like if: 1. λ 1 = 0?
More informationTemplate Matching Rigid Motion. Find transformation to align two images. Focus on geometric features
Template Matching Rigid Motion Find transformation to align two images. Focus on geometric features (not so much interesting with intensity images) Emphasis on tricks to make this efficient. Problem Definition
More informationData Representation in Visualisation
Data Representation in Visualisation Visualisation Lecture 4 Taku Komura Institute for Perception, Action & Behaviour School of Informatics Taku Komura Data Representation 1 Data Representation We have
More informationStructured Light II. Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov
Structured Light II Johannes Köhler Johannes.koehler@dfki.de Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov Introduction Previous lecture: Structured Light I Active Scanning Camera/emitter
More informationIterative SPECT reconstruction with 3D detector response
Iterative SPECT reconstruction with 3D detector response Jeffrey A. Fessler and Anastasia Yendiki COMMUNICATIONS & SIGNAL PROCESSING LABORATORY Department of Electrical Engineering and Computer Science
More informationAgenda. Rotations. Camera models. Camera calibration. Homographies
Agenda Rotations Camera models Camera calibration Homographies D Rotations R Y = Z r r r r r r r r r Y Z Think of as change of basis where ri = r(i,:) are orthonormal basis vectors r rotated coordinate
More informationME/CS 132: Introduction to Vision-based Robot Navigation! Low-level Image Processing" Larry Matthies"
ME/CS 132: Introduction to Vision-based Robot Navigation! Low-level Image Processing" Larry Matthies" lhm@jpl.nasa.gov, 818-354-3722" Announcements" First homework grading is done! Second homework is due
More informationCamera Calibration. Schedule. Jesus J Caban. Note: You have until next Monday to let me know. ! Today:! Camera calibration
Camera Calibration Jesus J Caban Schedule! Today:! Camera calibration! Wednesday:! Lecture: Motion & Optical Flow! Monday:! Lecture: Medical Imaging! Final presentations:! Nov 29 th : W. Griffin! Dec 1
More informationAnnouncements. Mosaics. How to do it? Image Mosaics
Announcements Mosaics Project artifact voting Project 2 out today (help session at end of class) http://www.destination36.com/start.htm http://www.vrseattle.com/html/vrview.php?cat_id=&vrs_id=vrs38 Today
More informationEN1610 Image Understanding Lab # 4: Corners, Interest Points, Hough Transform
EN1610 Image Understanding Lab # 4: Corners, Interest Points, Hough Transform The goal of this fourth lab is to ˆ Learn how to detect corners, and use them in a tracking application ˆ Learn how to describe
More informationRobert Collins CSE598G. Intro to Template Matching and the Lucas-Kanade Method
Intro to Template Matching and the Lucas-Kanade Method Appearance-Based Tracking current frame + previous location likelihood over object location current location appearance model (e.g. image template,
More informationImage Analysis. Edge Detection
Image Analysis Edge Detection Christophoros Nikou cnikou@cs.uoi.gr Images taken from: Computer Vision course by Kristen Grauman, University of Texas at Austin (http://www.cs.utexas.edu/~grauman/courses/spring2011/index.html).
More information